AI Agent StoreFrontiersMind · Provider documented
Lumma-Fev-27B
Choose labels or yes/no answers for records in English, Hindi, Tamil and Kannada. This downloadable model returns probabilities and can serve a ticket-routing workflow on your own hardware.
Released 2026-10-14 · First reviewed 2026-10-15 · Checked 2026-10-15.
We still need comparable independent tests. You can compare the confirmed features and limits below, but we cannot yet give this version an Agent Fit or Practical Value rating. Test it on records with known answers, including cases that should go to a person.
What you can use today
You download the model files and supply the hardware and software to run them. Capacity is the amount of information a request can contain; settings and available memory can limit what fits.
Exact checkpoint ID: FrontiersMind/Lumma-fev-27B. Built from Qwen3.8-27B. The provider trained and tested yes/no and choice questions; ordered score questions are accepted but untested. Image input requires the optional image package. Published comparisons are the developer’s evaluations, not independent evidence.
Apache 2.0 weights. The model card recommends about 55 GB of free GPU memory, typically an 80 GB card, or several GPUs. Install the provider’s software and test confidence thresholds on your own examples before automating decisions.
Shared information plus one question must fit within 8,192 tokens. Each question reads the shared information separately; answers do not change one another.
This is a local download, with no verified hosted token rate. Include hardware, electricity and maintenance when comparing it with an online API.
Provider release and specifications ↗
Check availability and plans ↗
Test it before switching
Give each model the same examples, tools and definition of success. Record correct outcomes, response time, retries and total cost. Include the time and hardware needed to run it.
Compare caching and long-context costs ↗